Learning Compressible 360° Video Isomers
Standard video encoders developed for conventional narrow field-of-view video are widely applied to 360° video as well, with reasonable results. However, while this approach commits arbitrarily to a projection of the spherical frames, we observe that some orientations of a 360° video, once projected, are more compressible than others. We introduce an approach to predict the sphere rotation that will yield the maximal compression rate. Given video clips in their original encoding, a convolutional neural network learns the association between a clipâs visual content and its compressibility at different rotations of a cubemap projection. Given a novel video, our learning-based approach efficiently infers the most compressible direction in one shot, without repeated rendering and compression of the source video. We validate our idea on thousands of video clips and multiple popular video codecs. The results show that this untapped dimension of 360° compression has substantial potentialââgoodâ rotations are typically 8â10% more compressible than bad ones, and our learning approach can predict them reliably 82% of the time.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning Compressible 360° Video Isomers
Standard video encoders developed for conventional narrow field-of-view video are widely applied to 360{\deg} video as well, with reasonable results. However, while this approach commits arbitrarily to a projection of th…
Compressible Motion Fields
Traditional video compression methods obtain a compact representation for image frames by computing coarse motion fields defined on patches of pixels called blocks, in order to compensate for the motion in the scene acro…
Motion CompensationOptical Flow EstimationVideo CompressionLearning with Compressible Priors
We describe probability distributions, dubbed compressible priors, whose independent and identically distributed (iid) realizations result in compressible signals. A signal is compressible when sorted magnitudes of its c…
Bayesian InferenceAtomComposer: Discovering Chemical Space from First Principles with Reinforcement Learning
Discovering novel stable molecules without training data remains a grand scientific challenge. Current molecular generative models are trained on large, pre-curated datasets, which introduce biases and limit exploration …
Reinforcement LearningThe compressible Neural Particle Method for Simulating Compressible Viscous Fluid Flows
Particle methods play an important role in computational fluid dynamics, but they are among the most difficult to implement and solve. The most common method is smoothed particle hydrodynamics, which is suitable for prob…